Similarity search profiles as a diagnostic tool for the analysis of virtual screening calculations. Xue, L., Godden, J. W., Stahura, F. L., & Bajorath, J. J.~Chem.~Inf.~Comput.~Sci., 44(4):1275--1281, 2004.
doi  abstract   bibtex   
An analysis method termed similarity search profiling has been developed to evaluate fingerprint-based virtual screening calculations. The analysis is based on systematic similarity search calculations using multiple template compounds over the entire value range of a similarity coefficient. In graphical representations, numbers of correctly identified hits and other detected database compounds are separately monitored. The resulting profiles make it possible to determine whether a virtual screening trial can in principle succeed for a given compound class, search tool, similarity metric, and selection criterion. As a test case, we have analyzed virtual screening calculations using a recently designed fingerprint on 23 different biological activity classes in a compound source database containing approximately 1.3 million molecules. Based on our predefined selection criteria, we found that virtual screening analysis was successful for 19 of 23 compound classes. Profile analysis also makes it possible to determine compound class-specific similarity threshold values for similarity searching.
@article{Xue:2004fk,
	Abstract = {An analysis method termed similarity search profiling has been developed to evaluate fingerprint-based virtual screening calculations. The analysis is based on systematic similarity search calculations using multiple template compounds over the entire value range of a similarity coefficient. In graphical representations, numbers of correctly identified hits and other detected database compounds are separately monitored. The resulting profiles make it possible to determine whether a virtual screening trial can in principle succeed for a given compound class, search tool, similarity metric, and selection criterion. As a test case, we have analyzed virtual screening calculations using a recently designed fingerprint on 23 different biological activity classes in a compound source database containing approximately 1.3 million molecules. Based on our predefined selection criteria, we found that virtual screening analysis was successful for 19 of 23 compound classes. Profile analysis also makes it possible to determine compound class-specific similarity threshold values for similarity searching.},
	Author = {Xue, Ling and Godden, Jeffrey W. and Stahura, Florence L. and Bajorath, J\"{u}rgen},
	Date = {2004 Jul-Aug},
	Date-Added = {2012-04-01 19:32:33 -0400},
	Date-Modified = {2012-04-01 19:33:01 -0400},
	Doi = {10.1021/ci040120g},
	Journal = {J.~Chem.~Inf.~Comput.~Sci.},
	Journal-Full = {Journal of chemical information and computer sciences},
	Mesh = {Databases, Factual; Drug Evaluation, Preclinical; Molecular Structure; Structure-Activity Relationship; User-Computer Interface},
	Number = {4},
	Pages = {1275--1281},
	Pmid = {15272835},
	Pst = {ppublish},
	Title = {Similarity search profiles as a diagnostic tool for the analysis of virtual screening calculations},
	Volume = {44},
	Year = {2004},
	Bdsk-Url-1 = {http://dx.doi.org/10.1021/ci040120g}}

Downloads: 0